Web service resource framework based computing service framework for computational grid applications

Authors:
Eui Heo;Kyung-Lang Park;Oh-Young Kwon;Oh-Kyung Kwon;Shin-Dug Kim
Affiliations:
Supercomputing Lab, Dept. of Computer Science, Yonsei University, Seoul, Korea;Supercomputing Lab, Dept. of Computer Science, Yonsei University, Seoul, Korea;Dept. of Computer Engineering, Korea University of Technology and Education, Chonan, Korea;Korea Institute of Science and Technology Information, Yusong, Daejeon, Korea;Supercomputing Lab, Dept. of Computer Science, Yonsei University, Seoul, Korea
Venue:
ISPA'06 Proceedings of the 2006 international conference on Frontiers of High Performance Computing and Networking
Year:
2006

Citing 5
Cited 0

Grid Services for Distributed System Integration

Computer
MPICH-G2: a Grid-enabled implementation of the Message Passing Interface

Journal of Parallel and Distributed Computing - Special issue on computational grids
GEMLCA: Grid Execution Management for Legacy Code Architecture Design

EUROMICRO '04 Proceedings of the 30th EUROMICRO Conference
How to Run Scientific Applications over Web Services

ICPPW '05 Proceedings of the 2005 International Conference on Parallel Processing Workshops
The impact of Web service integration on grid performance

HPDC '05 Proceedings of the High Performance Distributed Computing, 2005. HPDC-14. Proceedings. 14th IEEE International Symposium

Quantified Score

Hi-index	0.00

Visualization

Abstract

Grid and Web service technology can be used as a solution for the resource shortage problem. These two technologies are used to be applied to MPI (message passing interface) applications to design a framework to deploy MPI applications on OGSA (open Grid service architecture). In particular, we modeled MPI applications as WS-Resources. We call the WS-Resource “MPI resource” and it is composed of an MPI application and its associated dynamically created running environment. Thus, an MPI resource represents one MPI task. Through this model, MPI applications can be published to the world of the Grid. In addition, running environment is dynamically created from resources chosen among distributed idle resources on the Grid. Deployed MPI resources are utilized by other services. Especially in virtual organizations, MPI resources can have the roles responsible for computing task as computing resources for compute-intensive works and data resources for data-intensive works.